© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13717
    Prev
    Next
    INDEX
    Explanations

    steps or actions in setting up software configurations or controls

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    554
    +0.14
    0.5%
    1271
    +0.13
    0.5%
    1437
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1437
    +0.14
    0.02
    172
    +0.13
    0.02
    554
    +0.13
    0.02
    Negative Logits
    Ejemplos
    -0.55
    ciuta
    -0.54
     ideolog
    -0.53
     garant
    -0.51
     Noviembre
    -0.51
    ceptre
    -0.51
    cipais
    -0.51
     biograf
    -0.50
    Aplicación
    -0.49
     notor
    -0.49
    POSITIVE LOGITS
     settings
    1.27
     Settings
    1.20
    settings
    1.11
     setting
    1.08
     SETTINGS
    1.07
     Setting
    1.05
    Settings
    1.03
    setting
    0.99
    SETTINGS
    0.94
    Setting
    0.93
    Activations Density 0.065%

    No Known Activations